Yifan QiaoandClaude Fable 5.1 39724758e7 [Bugfix] GLM-5.3-Flash: launch the kpool paged MQA logits in the varlen mode its schedule was built with (#55270) ...

Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-25 00:13:55 +00:00

..

amd

[GLM5.3 Perf] Size the GLM-5 sparse indexer decode workspace, 3072 MiB GPU memory saved (#57701)

2026-09-19 16:57:01 -04:00

common

[Bugfix][Model][Spec Decode] Defer disposable GLM MTP head (#55442)

2026-09-22 20:08:27 +00:00

nvidia

[Bugfix] GLM-5.3-Flash: launch the kpool paged MQA logits in the varlen mode its schedule was built with (#55270)

2026-09-25 00:13:55 +00:00

__init__.py

[ROCm] [Bugfix] Enable Load and Inference of GLM-5.3-Flash Quark MXFP4 Checkpoint (#56176)

2026-09-16 01:25:29 +00:00

sparse_indexer.py

[Refactor][GLM-5.3-Flash] Move sparse_attn_indexer_kpool into the model folder and split AMD/NVIDIA (#55358)

2026-09-16 05:50:35 +00:00